Repozytorium publikacji - Politechnika Gdańska

In this paper we present our approach to RecSys Challenge 2015. Given a set of e-commerce events, the task is to predict whether a user will buy something in the current session and, if yes, which of the item will be bought. We show that the data preparation and enrichment are very important in finding the solution for the challenge and that simple ideas and intuitions could lead to satisfactory results. We also show that simple combination of well-known data mining algorithms could lead to improvement of values of metrics like root-square-mean error and mean absolute error in comparison to state-of-the-art prediction techniques.

Autorzy

• dr inż. Aleksandra Karpus link otwiera się w nowej karcie